modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-13 18:26:42
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 558
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-13 18:25:20
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
ihsanridzi/blockassist-bc-wiry_flexible_owl_1755681443
|
ihsanridzi
| 2025-08-20T09:43:44Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wiry flexible owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:43:41Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- wiry flexible owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
numind/NuMarkdown-8B-Thinking
|
numind
| 2025-08-20T09:42:17Z | 4,611 | 185 |
transformers
|
[
"transformers",
"safetensors",
"qwen2_5_vl",
"image-to-text",
"OCR",
"vision-language",
"VLM",
"Reasoning",
"document-to-markdown",
"qwen2.5",
"markdown",
"extraction",
"RAG",
"license:mit",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2025-07-29T18:39:08Z |
---
license: mit
base_model: Qwen/Qwen2.5-VL-7B
tags:
- OCR
- vision-language
- VLM
- Reasoning
- document-to-markdown
- qwen2.5
- markdown
- extraction
- RAG
model_name: NuMarkdown-8B-Thinking
library_name: transformers
pipeline_tag: image-to-text
---
<p align="center">
<a href="https://nuextract.ai/">
<img src="numind.svg" width="400" height="400"/>
</a>
</p>
<p align="center">
🖥️ <a href="https://nuextract.ai/">API / Platform</a>   |   🗣️ <a href="https://discord.gg/3tsEtJNCDe">Discord</a>   |   🔗 <a href="https://github.com/numindai/NuMarkdown">GitHub</a>   |   🤗 <a href="https://huggingface.co/spaces/numind/NuMarkdown-8b-Thinking">Demo</a>
</p>
---
# Reasoning comes to OCR 🧠✨📄🤘
**NuMarkdown-8B-Thinking** is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications. It generates thinking tokens to figure out the layout of the document before generating the Markdown file.
It is particularly good at understanding documents with weird layouts and complex tables. The number of thinking tokens can vary from 20% to 500% of the final answer, depending on the task difficulty.
**NuMarkdown-8B-Thinking** is a fine-tune of **Qwen 2.5-VL-7B** on synthetic Doc → Reasoning → Markdown examples, followed by an RL phase (GRPO) with a layout-centric reward.
Try it out in [the 🤗 space!](https://huggingface.co/spaces/numind/NuMarkdown-8b-Thinking)
## Results
**NuMarkdown-8B-Thinking** is outperforming generic non-reasoning models like GPT-4o and specialized OCR models like OCRFlux.
It is competitive against large reasoning closed-source models like Gemini 2.5.
### Arena ranking against popular alternatives (using trueskill-2 ranking system, with around 500 model-anonymized votes):
<p align="center">
| Rank | Model | μ | σ | μ − 3σ |
| ---- | --------------------------------------- | ----- | ---- | ------ |
| 🥇 1 | **gemini-flash-reasoning** | 26.75 | 0.80 | 24.35 |
| 🥈 2 | **NuMarkdown-reasoning** | 26.10 | 0.79 | 23.72 |
| 🥉 3 | **NuMarkdown-reasoning-w/o\_grpo** | 25.32 | 0.80 | 22.93 |
| 4 | **OCRFlux-3B** | 24.63 | 0.80 | 22.22 |
| 5 | **gpt-4o** | 24.48 | 0.80 | 22.08 |
| 6 | **gemini-flash-w/o\_reasoning** | 24.11 | 0.79 | 21.74 |
| 7 | **RolmoOCR** | 23.53 | 0.82 | 21.07 |
</p>
*We plan to realease a markdown arena, similar to llmArena, for complex document-to-markdown tasks to provide a tool to evaluate different solutions.*
### Win/Draw/Lose-rate against others models (image-only):
<p align="center">
<img src="bar plot.png" width="700"/>
</p>
## Training
1. **SFT**: Single epoch supervised fine-tuning on synthetic reasoning traces generated from public PDFs.
2. **RL (GRPO)**: RL phase using a layout-centric reward with difficult image examples.
## Example:
<p align="center">
<img src="ex1.png" width="500"/>
</p>
```
<think>
1. **Analyze the overall structure:** The document consists of two main sections, each containing a header, a set of bullet points, a title, a table, and a footer. The layout is consistent within each section but different between the two.
2. **Handle the first section header and bullet points:**
- The top left corner has "Generalitat de Catalunya Departament d'Educació Institut Gal·lecs". This is a consistent header and should be transcribed as a level 3 heading.
- The top right corner has "Curs 2021-22". This is a distinct header and should be transcribed as a level 3 heading.
- Below the header, there are four bullet points. These are standard list items. I will use Markdown's unordered list syntax (`- `).
3. **Process the first section's main content - Table 1:**
- **Identify table structure:** This is a complex table with a clear header row: "MATERIAL", "TÍTOL", "AUTOR", "EDITORIAL", "ISBN".
- **Determine columns:** There are 5 columns.
- **Handle merged cells:**
- "Llengua Catalana" spans two rows.
- "Llengua Castellana" spans three rows.
- "Anglès" spans two rows.
- **Populate table data:** Transcribe all text, including multi-line content within cells (e.g., "Babulinka Books\nEditorialCol·lecció: Pettes\nJoies per a Grans Lectors.\n2013").
- **Markdown table creation:** Use standard Markdown table syntax, ensuring correct alignment and handling of multi-line content within cells.
4. **Handle the first section's footer:**
- The footer contains "Codí: 04mp02", "Responsable: Coordinador Qualitat", "Versió: 5", "Full d'Informació a l'alumnat i famílies", "Aquest document pot quedar obsolet una vegada imprès", and "Pàgina 1 de 2". This is a simple text block at the bottom. I will transcribe it as a separate paragraph or list, maintaining the original layout if possible, but a simple paragraph is sufficient for a footer.
5. **Handle the second section header and bullet points:**
- The top left corner has "Generalitat de Catalunya Departament d'Educació Institut Gal·lecs". This is a consistent header and should be transcribed as a level 3 heading.
- The top right corner has "Curs 2021-22". This is a distinct header and should be transcribed as a level 3 heading.
- Below the header, there are no bullet points, but there is a table.
6. **Process the second section's main content - Table 2:**
- **Identify table structure:** This is a simpler table with a clear header row: "MATERIAL", "TÍTOL", "AUTOR", "EDITORIAL", "ISBN".
- **Determine columns:** There are 5 columns.
- **Populate table data:** Transcribe all text, including multi-line content within cells (e.g., "Projecte MOTIMATS-ONMAT (llicència digital) Tekman Books\nES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE").
- **Markdown table creation:** Use standard Markdown table syntax.
7. **Handle the second section's footer:**
- The footer contains "Codí: 04mp02", "Responsable: Coordinador Qualitat", "Versió: 5", "Full d'Informació a l'alumnat i famílies", "Aquest document pot quedar obsolet una vegada imprès", and "Pàgina 2 de 2". This is a simple text block at the bottom. I will transcribe it as a separate paragraph or list, maintaining the original layout if possible, but a simple paragraph is sufficient for a footer.
8. **Final review:** Check for any missed text, incorrect formatting, or issues with table alignment. Ensure all original content is present and accurately represented in GitHub-Flavored Markdown. The image placeholders are not needed as there are no images in the document.
</think>
<answer>
### Generalitat de Catalunya
### Departament d'Educació
### Institut Gal·lecs
### Curs 2021-22
- Els llibres de color blau indiquen que es manté respecte al curs anterior.
- Els llibres de color groc indiquen que es tracta d'un canvi per a aquest curs.
- Els llibres de color vermell indiquen que no s'han de comprar perquè van a càrrec del centre.
- Matèries sense llibre: Dossiers, llicències i el Kit de tecnologia s'hauran de pagar i de recollir a través de l'AMPA a partir de setembre.
# 1 ESO
| MATERIAL | TÍTOL | AUTOR | EDITORIAL | ISBN |
|---|---|---|---|---|
| Llengua Catalana | Punt Volat | | Castellnou (Didacta +) | 9788417803124 |
| | Duna, Diari d'un estiu. | Muriel Villanueva | Babulinka Books<br>EditorialCol·lecció: Pettes<br>Joies per a Grans Lectors.<br>2013 | 9788494159077 |
| | El nen que xatejava amb Jack Sparrow. | Francesc Puigpelat | Bromera<br>Col·lecció: L'Elefant. 2015 | 9788490264072 |
| Llengua Castellana | Proyecto Asterisco | | Castellnou (Didacta +) | 9788417803186 |
| | Manzanas rojas | Luis Matilla | Ed. Anaya | 978846673989 |
| | Fàbulas de Esopo | Jerry Pinkney | Vicens Vives | 978843671648 |
| Anglès | Think Ahead ESO 1. Student's book.<br>Think Ahead ESO 1. Workbook (cat). | | Burlington Books<br>Burlington Books | 9788925300662<br>9789925300686 |
Codí: 04mp02
Responsable: Coordinador Qualitat
Versió: 5
Full d'Informació a l'alumnat i famílies
Aquest document pot quedar obsolet una vegada imprès
Pàgina 1 de 2
### Generalitat de Catalunya
### Departament d'Educació
### Institut Gal·lecs
### Curs 2021-22
| MATERIAL | TÍTOL | AUTOR | EDITORIAL | ISBN |
|---|---|---|---|---|
| FRANCÈS | Nouvelle Génération A1-A2 | | Santillana | 9788490494745 |
| CIÈNCIES EXPERIMENTALS | Science Bits<br>ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE | | | 9788412213485 (llicència digital) |
| MATEMÀTIQUES | Projecte MOTIMATS-ONMAT (llicència digital) Tekman Books<br>ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE | | | |
| TECNOLOGIA | Tecnologia 1 ESO | TEIDE | | 9788430783175 |
| VISUAL I PLÀSTICA | SENSE LLIBRE-KIT DE MATERIAL | | | |
| CIÈNCIES SOCIALS | SENSE LLIBRE-dossier | | | |
Codí: 04mp02
Responsable: Coordinador Qualitat
Versió: 5
Full d'Informació a l'alumnat i famílies
Aquest document pot quedar obsolet una vegada imprès
Pàgina 2 de 2
</answer>
```
## Quick start:
## vLLM:
```
vllm serve numind/NuMarkdown-8B-Thinking --trust_remote_code --limit-mm-per-prompt image=1
```
```python
from openai import OpenAI
import base64
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
def encode_image(image_path):
"""
Encode the image file to base64 string
"""
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
base64_image = encode_image("image.png")
data_url = f"data:image/jpeg;base64,{base64_image}"
chat_response = client.chat.completions.create(
model="numind/NuMarkdown-8B-Thinking",
temperature=0.7,
messages=[
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {"url": data_url},
"min_pixels": 100 * 28 * 28,
"max_pixels": 5000 * 28 * 28,
},
],
},
]
)
result = chat_response.choices[0].message.content
reasoning = result.split("<think>")[1].split("</think>")[0]
answer = result.split("<answer>")[1].split("</answer>")[0]
print(answer)
```
## 🤗 Transformers:
```python
import torch
from PIL import Image
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
model_id = "numind/NuMarkdown-8B-reasoning"
processor = AutoProcessor.from_pretrained(
model_id,
trust_remote_code=True,
min_pixels=100*28*28, max_pixels=5000*28*28
)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
device_map="auto",
trust_remote_code=True,
)
img = Image.open("image.png").convert("RGB")
messages = [{
"role": "user",
"content": [
{"type": "image"},
],
}]
prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_input = processor(text=prompt, images=[img], return_tensors="pt").to(model.device)
with torch.no_grad():
model_output = model.generate(**model_input, temperature = 0.7, max_new_tokens=5000)
result = processor.decode(model_output[0])
reasoning = result.split("<think>")[1].split("</think>")[0]
answer = result.split("<answer>")[1].split("</answer>")[0]
print(answer)
```
|
chainway9/blockassist-bc-untamed_quick_eel_1755681134
|
chainway9
| 2025-08-20T09:40:58Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"untamed quick eel",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:40:53Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- untamed quick eel
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
katreiaht/speecht5_finetuned_ertan_tr
|
katreiaht
| 2025-08-20T09:39:36Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-audio
| 2025-08-20T09:20:09Z |
---
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_ertan_tr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# speecht5_finetuned_ertan_tr
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0+cu126
- Datasets 2.19.1
- Tokenizers 0.21.4
|
alessiodevoto/exp_att_stats_meta1_test2_10_100_4
|
alessiodevoto
| 2025-08-20T09:39:34Z | 0 | 0 | null |
[
"safetensors",
"model_hub_mixin",
"pytorch_model_hub_mixin",
"region:us"
] | null | 2025-08-20T09:39:33Z |
---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: [More Information Needed]
- Paper: [More Information Needed]
- Docs: [More Information Needed]
|
rourkerhotmail1/blockassist-bc-stalking_scruffy_walrus_1755680608
|
rourkerhotmail1
| 2025-08-20T09:39:18Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stalking scruffy walrus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:39:15Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stalking scruffy walrus
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755681600
|
Sayemahsjn
| 2025-08-20T09:39:07Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful feline octopus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:39:02Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- playful feline octopus
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Ferdi3425/blockassist-bc-amphibious_deadly_otter_1755682634
|
Ferdi3425
| 2025-08-20T09:38:32Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"amphibious deadly otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:38:01Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- amphibious deadly otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755682592
|
xinnn32
| 2025-08-20T09:37:05Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:36:55Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
alessiodevoto/exp_att_stats_meta_test2_10_100_4
|
alessiodevoto
| 2025-08-20T09:36:57Z | 0 | 0 | null |
[
"safetensors",
"model_hub_mixin",
"pytorch_model_hub_mixin",
"region:us"
] | null | 2025-08-20T09:29:49Z |
---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: [More Information Needed]
- Paper: [More Information Needed]
- Docs: [More Information Needed]
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755682509
|
kapalbalap
| 2025-08-20T09:36:12Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:36:00Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
lautan/blockassist-bc-gentle_patterned_goat_1755680769
|
lautan
| 2025-08-20T09:33:54Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gentle patterned goat",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:33:50Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gentle patterned goat
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aleebaster/blockassist-bc-sly_eager_boar_1755680881
|
aleebaster
| 2025-08-20T09:33:30Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"sly eager boar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:33:23Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- sly eager boar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
LarryAIDraw/hexerMinimalToon_v1
|
LarryAIDraw
| 2025-08-20T09:33:23Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-08-20T01:33:50Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/1882292/hexer-minimal-toon-or-mexes?modelVersionId=2130491
|
againeureka/causal_classifier_base_2025b
|
againeureka
| 2025-08-20T09:33:12Z | 0 | 0 | null |
[
"pytorch",
"roberta",
"generated_from_trainer",
"region:us"
] | null | 2025-08-20T06:02:34Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: causal_classifier_base_2025b
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# causal_classifier_base_2025b
This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6842
- Accuracy: 0.9226
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 84
- eval_batch_size: 84
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.6451 | 1.0 | 677 | 0.3905 | 0.8486 |
| 0.4548 | 2.0 | 1354 | 0.3248 | 0.8786 |
| 0.333 | 3.0 | 2031 | 0.3132 | 0.8862 |
| 0.2618 | 4.0 | 2708 | 0.2855 | 0.9133 |
| 0.2271 | 5.0 | 3385 | 0.3195 | 0.8981 |
| 0.169 | 6.0 | 4062 | 0.3678 | 0.8926 |
| 0.1417 | 7.0 | 4739 | 0.3716 | 0.9044 |
| 0.1325 | 8.0 | 5416 | 0.3965 | 0.9031 |
| 0.1056 | 9.0 | 6093 | 0.4048 | 0.9116 |
| 0.0914 | 10.0 | 6770 | 0.4088 | 0.9095 |
| 0.085 | 11.0 | 7447 | 0.4272 | 0.9192 |
| 0.0709 | 12.0 | 8124 | 0.4835 | 0.9074 |
| 0.0657 | 13.0 | 8801 | 0.4501 | 0.9129 |
| 0.0633 | 14.0 | 9478 | 0.4913 | 0.9082 |
| 0.0518 | 15.0 | 10155 | 0.4659 | 0.9188 |
| 0.05 | 16.0 | 10832 | 0.5005 | 0.9095 |
| 0.0438 | 17.0 | 11509 | 0.5048 | 0.9146 |
| 0.0391 | 18.0 | 12186 | 0.5279 | 0.9133 |
| 0.0363 | 19.0 | 12863 | 0.5297 | 0.9078 |
| 0.0366 | 20.0 | 13540 | 0.5633 | 0.9069 |
| 0.0308 | 21.0 | 14217 | 0.5911 | 0.9124 |
| 0.0294 | 22.0 | 14894 | 0.5519 | 0.9167 |
| 0.0282 | 23.0 | 15571 | 0.6248 | 0.9133 |
| 0.0223 | 24.0 | 16248 | 0.5584 | 0.9150 |
| 0.0241 | 25.0 | 16925 | 0.6267 | 0.9095 |
| 0.0213 | 26.0 | 17602 | 0.6172 | 0.9129 |
| 0.0197 | 27.0 | 18279 | 0.6328 | 0.9133 |
| 0.0186 | 28.0 | 18956 | 0.6634 | 0.9103 |
| 0.0158 | 29.0 | 19633 | 0.6469 | 0.9171 |
| 0.0155 | 30.0 | 20310 | 0.6782 | 0.9150 |
| 0.0131 | 31.0 | 20987 | 0.6496 | 0.9192 |
| 0.0119 | 32.0 | 21664 | 0.6960 | 0.9158 |
| 0.0102 | 33.0 | 22341 | 0.6467 | 0.9179 |
| 0.0107 | 34.0 | 23018 | 0.6842 | 0.9226 |
| 0.0119 | 35.0 | 23695 | 0.6582 | 0.9222 |
| 0.011 | 36.0 | 24372 | 0.6287 | 0.9188 |
| 0.0085 | 37.0 | 25049 | 0.6915 | 0.9192 |
| 0.0074 | 38.0 | 25726 | 0.7071 | 0.9179 |
| 0.0075 | 39.0 | 26403 | 0.6916 | 0.9192 |
| 0.0069 | 40.0 | 27080 | 0.6898 | 0.9141 |
| 0.0065 | 41.0 | 27757 | 0.7014 | 0.9184 |
| 0.0069 | 42.0 | 28434 | 0.7259 | 0.9171 |
| 0.0045 | 43.0 | 29111 | 0.7370 | 0.9192 |
| 0.0041 | 44.0 | 29788 | 0.7312 | 0.9192 |
| 0.0055 | 45.0 | 30465 | 0.7397 | 0.9196 |
| 0.0034 | 46.0 | 31142 | 0.7590 | 0.9201 |
| 0.0033 | 47.0 | 31819 | 0.7592 | 0.9184 |
| 0.003 | 48.0 | 32496 | 0.7662 | 0.9201 |
| 0.0033 | 49.0 | 33173 | 0.7650 | 0.9209 |
| 0.0033 | 50.0 | 33850 | 0.7634 | 0.9217 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.4.0+cu124
- Datasets 2.21.0
- Tokenizers 0.13.3
|
Ferdi3425/blockassist-bc-amphibious_deadly_otter_1755682263
|
Ferdi3425
| 2025-08-20T09:32:18Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"amphibious deadly otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:31:51Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- amphibious deadly otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
b0bbyhill/blockassist-bc-grunting_iridescent_anaconda_1755682156
|
b0bbyhill
| 2025-08-20T09:30:10Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"grunting iridescent anaconda",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:30:00Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- grunting iridescent anaconda
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755680546
|
vwzyrraz7l
| 2025-08-20T09:29:47Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tall hunting vulture",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:29:44Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tall hunting vulture
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Priyasi/Pretrain_TransVi_5
|
Priyasi
| 2025-08-20T09:29:41Z | 0 | 0 | null |
[
"safetensors",
"bert",
"custom_code",
"license:apache-2.0",
"region:us"
] | null | 2025-08-20T09:21:04Z |
---
license: apache-2.0
---
|
liukevin666/blockassist-bc-yawning_striped_cassowary_1755681952
|
liukevin666
| 2025-08-20T09:27:30Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"yawning striped cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:27:05Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- yawning striped cassowary
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
vchildress/my-great-gpt2-review-model
|
vchildress
| 2025-08-20T09:27:10Z | 9 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:distilbert/distilgpt2",
"base_model:finetune:distilbert/distilgpt2",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-14T13:12:12Z |
---
library_name: transformers
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: my-great-gpt2-review-model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my-great-gpt2-review-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6124
- Model Preparation Time: 0.0019
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.000891
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 0.3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
| 1.6504 | 0.3001 | 3093 | 1.6124 | 0.0019 |
### Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4
|
duyntnet/Magro-7b-v1.1-imatrix-GGUF
|
duyntnet
| 2025-08-20T09:26:47Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"imatrix",
"Magro-7b-v1.1",
"text-generation",
"en",
"arxiv:2306.01708",
"license:other",
"region:us",
"conversational"
] |
text-generation
| 2025-08-20T08:33:16Z |
---
license: other
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- transformers
- gguf
- imatrix
- Magro-7b-v1.1
---
Quantizations of https://huggingface.co/Sakalti/Magro-7b-v1.1
### Open source inference clients/UIs
* [llama.cpp](https://github.com/ggerganov/llama.cpp)
* [KoboldCPP](https://github.com/LostRuins/koboldcpp)
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [jan](https://github.com/menloresearch/jan)
* [ik_llama.cpp](https://github.com/ikawrakow/ik_llama.cpp)
* [croco.cpp](https://github.com/Nexesenex/croco.cpp)
### Closed source inference clients/UIs
* [LM Studio](https://lmstudio.ai/)
* More will be added...
---
# From original readme
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) as a base.
### Models Merged
The following models were included in the merge:
* [Sakalti/magro-7B](https://huggingface.co/Sakalti/magro-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Sakalti/magro-7B
parameters:
weight: 1
density: 1
merge_method: ties
base_model: HuggingFaceH4/zephyr-7b-alpha
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
dtype: bfloat16
```
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755681944
|
xinnn32
| 2025-08-20T09:26:17Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:26:07Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755681900
|
kapalbalap
| 2025-08-20T09:25:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:25:38Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Ferdi3425/blockassist-bc-amphibious_deadly_otter_1755681795
|
Ferdi3425
| 2025-08-20T09:24:39Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"amphibious deadly otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:24:11Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- amphibious deadly otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Willy030125/whisper_large_v3_turbo_noise_redux_v2
|
Willy030125
| 2025-08-20T09:24:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:Willy030125/ambient_noise_audio",
"base_model:openai/whisper-large-v3-turbo",
"base_model:finetune:openai/whisper-large-v3-turbo",
"license:mit",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2025-08-20T04:15:30Z |
---
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- generated_from_trainer
datasets:
- Willy030125/ambient_noise_audio
model-index:
- name: whisper_large_v3_turbo_noise_redux_v2
results: []
pipeline_tag: automatic-speech-recognition
library_name: transformers
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper_large_v3_turbo_noise_redux_v2
This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the ambient_noise_audio dataset.
It achieves the following results on the evaluation set:
- Loss: 6.8827
## Model description
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 6
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 11.0793 | 1.0 | 12 | 10.8135 |
| 10.6542 | 2.0 | 24 | 10.5037 |
| 10.4376 | 3.0 | 36 | 10.3954 |
| 10.2174 | 4.0 | 48 | 9.9744 |
| 9.7778 | 5.0 | 60 | 9.5521 |
| 9.3734 | 6.0 | 72 | 9.1692 |
| 9.0088 | 7.0 | 84 | 8.8258 |
| 8.6836 | 8.0 | 96 | 8.5225 |
| 8.399 | 9.0 | 108 | 8.2601 |
| 8.1554 | 10.0 | 120 | 8.0387 |
| 7.9527 | 11.0 | 132 | 7.8584 |
| 7.7913 | 12.0 | 144 | 7.7191 |
| 7.6702 | 13.0 | 156 | 7.6199 |
| 7.5894 | 14.0 | 168 | 7.5602 |
| 7.5475 | 15.0 | 180 | 7.5394 |
| 7.5068 | 16.0 | 192 | 7.4662 |
| 7.4412 | 17.0 | 204 | 7.4174 |
| 7.407 | 18.0 | 216 | 7.4003 |
| 7.3431 | 19.0 | 228 | 7.2668 |
| 7.2094 | 20.0 | 240 | 7.1460 |
| 7.0999 | 21.0 | 252 | 7.0497 |
| 7.0143 | 22.0 | 264 | 6.9762 |
| 6.9508 | 23.0 | 276 | 6.9245 |
| 6.9086 | 24.0 | 288 | 6.8935 |
| 6.8869 | 25.0 | 300 | 6.8827 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.4.1+cu124
- Datasets 2.18.0
- Tokenizers 0.15.2
|
koloni/blockassist-bc-deadly_graceful_stingray_1755680152
|
koloni
| 2025-08-20T09:23:38Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:23:34Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- deadly graceful stingray
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
raniero/test-instruct
|
raniero
| 2025-08-20T09:22:22Z | 0 | 0 | null |
[
"safetensors",
"region:us"
] | null | 2025-08-20T06:22:59Z |
# LoRA — Instruction SFT
- **Task ID:** unknown
- **Base model:** mistralai/Mistral-7B-Instruct-v0.2
- **SHA256 (adapter):** `a1408cdd2b34b7198ba15b5b2fadf94714d4768edc7057116cb0c3bfc6f363ec`
- **Repo:** raniero/test-instruct
Questa repo contiene SOLO gli adapter LoRA richiesti dai validator Subnet 56.
|
SwetaJena/llama-3.2-1B-phoenix_numbers_student_12
|
SwetaJena
| 2025-08-20T09:21:17Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/Llama-3.2-1B-Instruct",
"base_model:finetune:unsloth/Llama-3.2-1B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T09:21:12Z |
---
base_model: unsloth/Llama-3.2-1B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** SwetaJena
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Llama-3.2-1B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
dinesh-001/whisper_finetune_premier_v0
|
dinesh-001
| 2025-08-20T09:21:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T09:21:05Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
indoempatnol/blockassist-bc-fishy_wary_swan_1755680049
|
indoempatnol
| 2025-08-20T09:21:03Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"fishy wary swan",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:20:59Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- fishy wary swan
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VoilaRaj/81_itkf0n
|
VoilaRaj
| 2025-08-20T09:20:59Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-20T09:16:52Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
Nerva1228/hehua
|
Nerva1228
| 2025-08-20T09:19:29Z | 0 | 0 |
diffusers
|
[
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] |
text-to-image
| 2025-08-20T09:19:27Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: hehua
---
# Hehua
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `hehua` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "hehua",
"lora_weights": "https://huggingface.co/Nerva1228/hehua/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Nerva1228/hehua', weight_name='lora.safetensors')
image = pipeline('hehua').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/Nerva1228/hehua/discussions) to add images that show off what you’ve made with this LoRA.
|
VIDEOS-18-Zarina-anjoulie-viral-video-Clip/Orginal.full.Videos.Zarina.anjoulie.viral.video.Official.Tutorial
|
VIDEOS-18-Zarina-anjoulie-viral-video-Clip
| 2025-08-20T09:18:34Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T09:18:14Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5xr5mb3e?leaked-videos/" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
|
coelacanthxyz/blockassist-bc-finicky_thriving_grouse_1755679798
|
coelacanthxyz
| 2025-08-20T09:17:36Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"finicky thriving grouse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:17:31Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- finicky thriving grouse
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755681287
|
kapalbalap
| 2025-08-20T09:15:59Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:15:44Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
yaelahnal/blockassist-bc-mute_clawed_crab_1755681155
|
yaelahnal
| 2025-08-20T09:14:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mute clawed crab",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:13:35Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- mute clawed crab
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
calegpedia/blockassist-bc-stealthy_slimy_rooster_1755679656
|
calegpedia
| 2025-08-20T09:12:56Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stealthy slimy rooster",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:12:52Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stealthy slimy rooster
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755681109
|
kapalbalap
| 2025-08-20T09:12:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:12:41Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VoilaRaj/81_w138mX
|
VoilaRaj
| 2025-08-20T09:12:27Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-20T09:08:17Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
Mozilla/test-llama
|
Mozilla
| 2025-08-20T09:11:57Z | 0 | 0 | null |
[
"gguf",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T09:11:18Z |
---
license: apache-2.0
---
|
chainway9/blockassist-bc-untamed_quick_eel_1755679237
|
chainway9
| 2025-08-20T09:07:02Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"untamed quick eel",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:06:58Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- untamed quick eel
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
flemmingpetter2/blockassist-bc-hardy_subtle_snake_1755678631
|
flemmingpetter2
| 2025-08-20T09:03:41Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"hardy subtle snake",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:03:38Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- hardy subtle snake
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
lautan/blockassist-bc-gentle_patterned_goat_1755678683
|
lautan
| 2025-08-20T09:01:05Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gentle patterned goat",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:01:01Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gentle patterned goat
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
mradermacher/Rubicon-Preview-i1-GGUF
|
mradermacher
| 2025-08-20T09:00:58Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:inclusionAI/Rubicon-Preview",
"base_model:quantized:inclusionAI/Rubicon-Preview",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-08-20T04:05:45Z |
---
base_model: inclusionAI/Rubicon-Preview
language:
- en
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
weighted/imatrix quants of https://huggingface.co/inclusionAI/Rubicon-Preview
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Rubicon-Preview-i1-GGUF).***
static quants are available at https://huggingface.co/mradermacher/Rubicon-Preview-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own qwuants) |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ1_S.gguf) | i1-IQ1_S | 6.5 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ2_S.gguf) | i1-IQ2_S | 9.4 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 11.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.7 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ3_S.gguf) | i1-IQ3_S | 13.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q4_1.gguf) | i1-Q4_1 | 19.3 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF/resolve/main/Rubicon-Preview.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
dongjuu/gemma-3-12b-it-Rude-LORA
|
dongjuu
| 2025-08-20T08:56:57Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T08:56:48Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755678591
|
lisaozill03
| 2025-08-20T08:56:09Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:56:06Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
PatrickBAI/checkpoint
|
PatrickBAI
| 2025-08-20T08:55:38Z | 0 | 0 | null |
[
"safetensors",
"license:apache-2.0",
"region:us"
] | null | 2025-08-20T08:54:37Z |
---
license: apache-2.0
---
|
kojeklollipop/blockassist-bc-spotted_amphibious_stork_1755678400
|
kojeklollipop
| 2025-08-20T08:55:09Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"spotted amphibious stork",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:55:05Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- spotted amphibious stork
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755678318
|
vwzyrraz7l
| 2025-08-20T08:54:03Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tall hunting vulture",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:54:00Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tall hunting vulture
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
csukuangfj/kitten-nano-en-v0_1-fp16
|
csukuangfj
| 2025-08-20T08:52:16Z | 0 | 0 | null |
[
"onnx",
"region:us"
] | null | 2025-08-07T03:41:14Z |
# Introduction
See also https://github.com/KittenML/KittenTTS
|
mang3dd/blockassist-bc-tangled_slithering_alligator_1755678302
|
mang3dd
| 2025-08-20T08:51:53Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tangled slithering alligator",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:51:49Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tangled slithering alligator
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
zypchn/swinv2-tiny-patch4-window8-256
|
zypchn
| 2025-08-20T08:51:12Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"swinv2",
"image-classification",
"generated_from_trainer",
"base_model:microsoft/swinv2-tiny-patch4-window8-256",
"base_model:finetune:microsoft/swinv2-tiny-patch4-window8-256",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2025-08-20T08:51:07Z |
---
library_name: transformers
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swinv2-tiny-patch4-window8-256
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# swinv2-tiny-patch4-window8-256
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3645
- Accuracy: 0.9556
- Weighted Precision: 0.9618
- Macro Precision: 0.8993
- Sensitivity: 0.9667
- Specificity: 0.9533
- Weighted F1: 0.9571
- Macro F1: 0.9258
- Auc: 0.9891
- Mcc: 0.8572
- J Stat: 0.9200
- Confusion Matrix: [[143, 7], [1, 29]]
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5.7518568938272085e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.02871528165192935
- num_epochs: 10
- label_smoothing_factor: 0.17582959541343296
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted Precision | Macro Precision | Sensitivity | Specificity | Weighted F1 | Macro F1 | Auc | Mcc | J Stat | Confusion Matrix |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------------------:|:---------------:|:-----------:|:-----------:|:-----------:|:--------:|:------:|:------:|:------:|:-----------------------:|
| 0.4314 | 1.0 | 188 | 0.3687 | 0.9547 | 0.9551 | 0.9387 | 0.9231 | 0.9658 | 0.9549 | 0.9415 | 0.9769 | 0.8831 | 0.8889 | [[1074, 38], [30, 360]] |
| 0.3907 | 2.0 | 376 | 0.3506 | 0.9660 | 0.9659 | 0.9638 | 0.9077 | 0.9865 | 0.9657 | 0.9550 | 0.9829 | 0.9107 | 0.8942 | [[1097, 15], [36, 354]] |
| 0.3354 | 3.0 | 564 | 0.3358 | 0.9767 | 0.9768 | 0.9782 | 0.9282 | 0.9937 | 0.9765 | 0.9691 | 0.9898 | 0.9390 | 0.9219 | [[1105, 7], [28, 362]] |
| 0.3558 | 4.0 | 752 | 0.3328 | 0.9787 | 0.9788 | 0.9804 | 0.9333 | 0.9946 | 0.9785 | 0.9718 | 0.9926 | 0.9442 | 0.9279 | [[1106, 6], [26, 364]] |
| 0.3284 | 5.0 | 940 | 0.3292 | 0.9814 | 0.9814 | 0.9831 | 0.9410 | 0.9955 | 0.9812 | 0.9754 | 0.9970 | 0.9513 | 0.9365 | [[1107, 5], [23, 367]] |
| 0.3294 | 6.0 | 1128 | 0.3229 | 0.9840 | 0.9841 | 0.9849 | 0.9513 | 0.9955 | 0.9839 | 0.9790 | 0.9976 | 0.9582 | 0.9468 | [[1107, 5], [19, 371]] |
| 0.3142 | 7.0 | 1316 | 0.3100 | 0.9927 | 0.9927 | 0.9925 | 0.9795 | 0.9973 | 0.9927 | 0.9904 | 0.9988 | 0.9809 | 0.9768 | [[1109, 3], [8, 382]] |
| 0.3116 | 8.0 | 1504 | 0.3059 | 0.9953 | 0.9953 | 0.9952 | 0.9872 | 0.9982 | 0.9953 | 0.9939 | 0.9993 | 0.9879 | 0.9854 | [[1110, 2], [5, 385]] |
| 0.3075 | 9.0 | 1692 | 0.3048 | 0.9960 | 0.9960 | 0.9956 | 0.9897 | 0.9982 | 0.9960 | 0.9948 | 0.9999 | 0.9896 | 0.9879 | [[1110, 2], [4, 386]] |
| 0.2981 | 10.0 | 1880 | 0.3046 | 0.9960 | 0.9960 | 0.9956 | 0.9897 | 0.9982 | 0.9960 | 0.9948 | 0.9999 | 0.9896 | 0.9879 | [[1110, 2], [4, 386]] |
### Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2
|
koloni/blockassist-bc-deadly_graceful_stingray_1755678290
|
koloni
| 2025-08-20T08:51:01Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:50:57Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- deadly graceful stingray
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
unitova/blockassist-bc-zealous_sneaky_raven_1755678067
|
unitova
| 2025-08-20T08:48:03Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"zealous sneaky raven",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:47:59Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- zealous sneaky raven
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
alekgomez/qwen3-4b-ft-v2
|
alekgomez
| 2025-08-20T08:47:31Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T08:32:00Z |
---
base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** alekgomez
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
18-Arovi-Nusrat-Ridhi-Viral-Video-links/New.full.videos.Arovi.Nusrat.Ridhi.Viral.Video.Official.Tutorial
|
18-Arovi-Nusrat-Ridhi-Viral-Video-links
| 2025-08-20T08:45:30Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T08:45:20Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?leaked-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
|
prashantsh/SmolLM2-FT-MyDataset
|
prashantsh
| 2025-08-20T08:45:26Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"trl",
"smol-course",
"module_1",
"sft",
"conversational",
"base_model:HuggingFaceTB/SmolLM2-135M",
"base_model:finetune:HuggingFaceTB/SmolLM2-135M",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T08:45:00Z |
---
base_model: HuggingFaceTB/SmolLM2-135M
library_name: transformers
model_name: SmolLM2-FT-MyDataset
tags:
- generated_from_trainer
- trl
- smol-course
- module_1
- sft
licence: license
---
# Model Card for SmolLM2-FT-MyDataset
This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="prashantsh/SmolLM2-FT-MyDataset", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/prashant1983-sh-whale-cloud/huggingface/runs/i4d464hv)
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.8.0+cu126
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
coelacanthxyz/blockassist-bc-finicky_thriving_grouse_1755677792
|
coelacanthxyz
| 2025-08-20T08:45:16Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"finicky thriving grouse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:45:10Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- finicky thriving grouse
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
goodragon/gemma-3-12b-it-Rude-LORA
|
goodragon
| 2025-08-20T08:43:04Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T08:42:54Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
calegpedia/blockassist-bc-stealthy_slimy_rooster_1755677847
|
calegpedia
| 2025-08-20T08:42:31Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stealthy slimy rooster",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:42:28Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stealthy slimy rooster
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
sbhnmb/gemma-3n-PersianCTG
|
sbhnmb
| 2025-08-20T08:41:52Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gemma3n",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T08:41:37Z |
---
base_model: unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gemma3n
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** sbhnmb
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
This gemma3n model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Donchocho/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_tricky_dolphin
|
Donchocho
| 2025-08-20T08:41:05Z | 106 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am graceful_tricky_dolphin",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-07-23T09:20:04Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am graceful_tricky_dolphin
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
govtech/lionguard-2
|
govtech
| 2025-08-20T08:40:43Z | 18,918 | 0 | null |
[
"safetensors",
"lionguard2",
"classifier",
"safety",
"moderation",
"multilingual",
"text-classification",
"custom_code",
"en",
"ms",
"ta",
"zh",
"license:other",
"region:us"
] |
text-classification
| 2025-06-30T05:54:42Z |
---
license: other
license_name: govtech-singapore
license_link: LICENSE
language:
- en
- ms
- ta
- zh
pipeline_tag: text-classification
tags:
- classifier
- safety
- moderation
- multilingual
---
# LionGuard 2
LionGuard 2 is a multilingual content moderation classifier tuned for English/Singlish, Chinese, Malay, and Tamil in the Singapore context.
It leverages OpenAI’s `text-embedding-3-large` with a multi-head classifier to return fine-grained scores for the following categories:
- Overall safety (`binary`)
- Hate (`hateful_l1`, `hateful_l2`)
- Insults (`insults`)
- Sexual content (`sexual_l1`, `sexual_l2`)
- Physical violence (`physical_violence`)
- Self-harm (`self_harm_l1`, `self_harm_l2`)
- Other misconduct (`all_other_misconduct_l1`, `all_other_misconduct_l2`)
---
# Taxonomy
| S/N | Category | Level | Description | Example |
|-----|-----------------------|-----------------------------------------|-----------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| **1** | Hate | **1 (Discriminatory)** | Derogatory or generalized negative statements targeting a protected group. | “All Chinese people are so scheming.”<br>“Malays are always late and lazy.”<br>“Indians are too noisy; I avoid them whenever possible.” |
| | | **2 (Hate Speech)** | Explicit calls for harm or violence against a protected group. | “We should kick all Chinese people out of the country.”<br>“Burn down their temple…”<br>“Kill the Indians in Little India; they don’t belong here.” |
| **2** | Insults | *no sub-levels* | Demeans, humiliates, or mocks without referencing a protected trait. | “You’re so dumb, you probably failed your PSLE.”<br>“Your singing is worse than karaoke at a dodgy KTV.” |
| **3** | Sexual | **1 (Not appropriate for minors)** | Mild-to-moderate sexual content. | “Let’s talk about how condoms work.” <br>“We had a one-night stand last weekend.” |
| | | **2 (Not appropriate for all ages)** | Explicit or graphic sexual content. | “Always think they very yandao … but actually is just one ** bin.” |
| **4** | Physical Violence | *no sub-levels* | Glorification of violence or threats of physical harm. | “If I see him at Clarke Quay, I’m going to whack him.”<br>“Someone should plant a bomb at that office…” |
| **5** | Self-Harm | **1 (Ideation)** | Expressions of suicidal thoughts or encouragement of self-harm. | “I’m so stressed … I feel like ending it all.”<br>“Failing my poly exams made me want to cut myself.” |
| | | **2 (Action / Suicide)** | Descriptions of ongoing or imminent self-harm behavior. | “I’ve locked myself in my room and taken a bunch of pills.”<br>“I’m on the rooftop at Toa Payoh, ready to jump.” |
| **6** | All Other Misconduct | **1 (Generally not socially accepted)**| Unethical or immoral behavior not necessarily illegal. | “Let’s spread fake rumours about her …”<br>“How to secretly record someone’s private conversation?” |
| | | **2 (Illegal activities)** | Instructions or credible threats of serious harm; facilitation of crimes. | “Anyone know where to buy illegal knives in Geylang?”<br>“Let’s hack that e-commerce site to get credit card details.” |
---
# Usage
```python
import os
import numpy as np
from transformers import AutoModel
from openai import OpenAI
# Load model directly from HF
model = AutoModel.from_pretrained(
"govtech/lionguard-2",
trust_remote_code=True
)
# Get OpenAI embeddings (users to input their own OpenAI API key)
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
response = client.embeddings.create(
input="Hello, world!", # users to input their own text
model="text-embedding-3-large",
dimensions=1536 # dimensions of the embedding
)
embeddings = np.array([data.embedding for data in response.data])
# Run LionGuard 2
results = model.predict(embeddings)
```
|
aralper18/blockassist-bc-gilded_tangled_albatross_1755679053
|
aralper18
| 2025-08-20T08:38:33Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gilded tangled albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:38:24Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gilded tangled albatross
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
yaelahnal/blockassist-bc-mute_clawed_crab_1755679016
|
yaelahnal
| 2025-08-20T08:38:05Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mute clawed crab",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:37:47Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- mute clawed crab
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
sdagsadgd/blockassist-bc-sedate_squeaky_salamander_1755675680
|
sdagsadgd
| 2025-08-20T08:35:36Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"sedate squeaky salamander",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:35:21Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- sedate squeaky salamander
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755677742
|
Sayemahsjn
| 2025-08-20T08:34:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful feline octopus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:34:46Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- playful feline octopus
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kongleehan/my_awesome_video_cls_model
|
kongleehan
| 2025-08-20T08:34:36Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"videomae",
"video-classification",
"generated_from_trainer",
"base_model:MCG-NJU/videomae-base",
"base_model:finetune:MCG-NJU/videomae-base",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2025-08-20T08:34:14Z |
---
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_video_cls_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_video_cls_model
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2957
- Accuracy: 0.9143
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 1200
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.0926 | 0.25 | 300 | 1.9448 | 0.3286 |
| 0.2963 | 1.25 | 600 | 0.7159 | 0.7429 |
| 0.0149 | 2.25 | 900 | 0.5006 | 0.8571 |
| 0.0027 | 3.25 | 1200 | 0.2957 | 0.9143 |
### Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4
|
AmirRghp/distilbert-base-uncasedimdb-text-classification
|
AmirRghp
| 2025-08-20T08:33:33Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"distilbert",
"text-classification",
"code",
"movie",
"en",
"dataset:shawhin/imdb-truncated",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-08-18T12:38:24Z |
---
library_name: transformers
tags:
- code
- movie
license: mit
datasets:
- shawhin/imdb-truncated
language:
- en
metrics:
- accuracy
- f1
- precision
- recall
- confusion_matrix
base_model:
- distilbert/distilbert-base-uncased
pipeline_tag: text-classification
---
# Model Card for IMDB Movie Review Classifier
This model is built for classifying movie reviews from the IMDB dataset into positive or negative categories. It uses the Hugging Face's `DistilBERT` model, a lighter version of BERT, for text classification tasks.
## Model Details
### Model Description
This model is fine-tuned for binary classification, trained on the IMDb dataset, and can predict whether a given review is positive or negative. It utilizes the `distilbert-base-uncased` model, a pre-trained transformer-based architecture.
- **Developed by:** Amirreza Gholipour
- **Funded by:** Amirreza Gholipour
- **Model type:** Transformer-based Text Classifier
- **Language(s) (NLP):** English
- **License:** MIT
- **Finetuned from model:** distilbert-base-uncased
## Uses
### Direct Use
This model can be used directly for classifying movie reviews. Given an IMDB review, the model will return a sentiment classification: positive or negative. The input text is tokenized, passed through the `DistilBERT` model, and the output is processed to classify the review sentiment.
### Downstream Use [optional]
The model can be fine-tuned further on other similar datasets to specialize it for different domains, such as classifying product reviews, news sentiment, or other text-based sentiment analysis tasks.
### Out-of-Scope Use
This model is not intended for use in detecting sarcasm, irony, or more nuanced sentiment expressions that require deeper contextual understanding. It may not perform well on non-English reviews.
## Bias, Risks, and Limitations
The model is trained on the IMDb dataset, which may introduce bias due to the nature of the content of movie reviews. It might not generalize well to domains outside of movie review sentiment classification. The dataset could be biased in terms of the types of movies reviewed (e.g., biased toward Hollywood blockbusters).
### Recommendations
Users should ensure they are aware of potential biases in the training data. The model should not be relied on for applications requiring high accuracy in specialized domains or nuanced text understanding.
## How to Get Started with the Model
```python
from transformers import pipeline
# Load the pre-trained model
classifier = pipeline('text-classification', model='AmirRghp/distilbert-base-uncasedimdb-text-classification')
# Classify a sample text
text = "The movie was absolutely amazing and I loved every minute of it!"
result = classifier(text)
print(result)
```
## Training Details
### Training Data
The model was trained on the IMDb dataset, a collection of 50,000 movie reviews categorized as either positive or negative.
- Dataset: IMDb dataset
- Number of samples: 50,000
- Categories: Positive, Negative
- Data Preprocessing: Tokenization and padding were applied to the raw text data to ensure compatibility with the DistilBERT model.
### Training Procedure
#### Preprocessing [optional]
The text data is tokenized using the DistilBERT tokenizer.
#### Training Hyperparameters
- Learning rate: 2e-5
- Batch size: 4
- Epochs: 5
#### Speeds, Sizes, Times [optional]
Training was conducted on a GPU with the following specifications:
- Hardware Type: Nvidia RTX 5060 TI
- Training Time: 5 Min
## Evaluation
The model was evaluated on accuracy, F1 score, precision, recall, and confusion matrix metrics. Here are the key evaluation results:
- Accuracy: 89.2%
- F1 Score: 0.89
- Precision: 0.88
- Recall: 0.90
#### Summary
The model performs well on the IMDb dataset, with a high accuracy rate and strong performance across other metrics. It’s ready for use in practical sentiment analysis tasks.
## Technical Specifications [optional]
### Model Architecture and Objective
The model is based on the DistilBERT architecture, which is a smaller and faster variant of the BERT model, designed to provide similar performance with fewer parameters.
- Architecture: Transformer-based encoder-decoder model
- Objective: Binary classification of text (positive or negative sentiment)
### Compute Infrastructure
- Hardware: Nvidia RTX 5060 TI
- Libraries: Hugging Face Transformers, PyTorch
## More Information [optional]
For more details on the model architecture and training, please refer to the Hugging Face documentation
## Model Card Authors [optional]
- Author: Amirreza Gholipour
- Contact: [](https://www.linkedin.com/in/amirreza-gholipour-11a05a323/)
|
Orginals-Uppal-Farm-Girl-Viral-Video-Links/New.full.videos.Uppal.Farm.Girl.Viral.Video.Official.Tutorial
|
Orginals-Uppal-Farm-Girl-Viral-Video-Links
| 2025-08-20T08:33:26Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T08:33:16Z |
<a href="https://sdu.sk/AyL"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝗦𝗶𝗴𝗻 𝗨𝗽 𝘁𝗼 𝙁𝙪𝙡𝙡 𝗪𝗮𝘁𝗰𝗵 𝙑𝙞𝙙𝙚𝙤❤️❤️)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►✅𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐥𝐢𝐧𝐤)</a>
|
Sunbird/qwen3-14b-ug40-sft-translation-plus-multilingual-tasks-merged
|
Sunbird
| 2025-08-20T08:32:27Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T08:15:06Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
bimabk/053c182c-e9ca-420e-b9fd-22199c23b1cb
|
bimabk
| 2025-08-20T08:32:26Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"base_model:adapter:unsloth/smollm-1.7b-bnb-4bit",
"lora",
"sft",
"transformers",
"trl",
"unsloth",
"text-generation",
"arxiv:1910.09700",
"region:us"
] |
text-generation
| 2025-08-20T08:32:20Z |
---
base_model: unsloth/smollm-1.7b-bnb-4bit
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:unsloth/smollm-1.7b-bnb-4bit
- lora
- sft
- transformers
- trl
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.17.0
|
vuitton/LouisVuitton_model5
|
vuitton
| 2025-08-20T08:30:43Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-20T08:24:45Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
sehun96/gemma-3-12b-it-Rude-LORA
|
sehun96
| 2025-08-20T08:28:42Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T08:28:36Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
playdatakoo/omar-ax-lora-skt-4.0
|
playdatakoo
| 2025-08-20T08:27:02Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"lora",
"skt",
"korean",
"ax",
"ko",
"base_model:skt/A.X-4.0-Light",
"base_model:adapter:skt/A.X-4.0-Light",
"region:us"
] | null | 2025-08-20T08:26:41Z |
---
base_model: skt/A.X-4.0-Light
tags:
- lora
- peft
- skt
- korean
- ax
language:
- ko
library_name: peft
---
# Omar AX LoRA Adapter for SKT A.X-4.0-Light
This is a LoRA adapter fine-tuned for the Korean language model.
## Model Details
- **Base Model**: [skt/A.X-4.0-Light](https://huggingface.co/skt/A.X-4.0-Light)
- **LoRA Rank**: 24
- **LoRA Alpha**: 12
- **LoRA Dropout**: 0.1
- **Target Modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
- **Task Type**: CAUSAL_LM
## Usage with vLLM
INFO 08-20 08:26:21 [__init__.py:241] Automatically detected platform cuda.
[1;36m(APIServer pid=15975)[0;0m INFO 08-20 08:26:24 [api_server.py:1805] vLLM API server version 0.10.1
[1;36m(APIServer pid=15975)[0;0m INFO 08-20 08:26:24 [utils.py:326] non-default args: {'model_tag': 'skt/A.X-4.0-Light', 'lora_modules': [LoRAModulePath(name='omar_ax', path='playdatakoo/omar-ax-lora-skt-4.0', base_model_name=None)], 'model': 'skt/A.X-4.0-Light', 'enable_lora': True}
[1;36m(APIServer pid=15975)[0;0m INFO 08-20 08:26:30 [__init__.py:711] Resolved architecture: Qwen2ForCausalLM
[1;36m(APIServer pid=15975)[0;0m INFO 08-20 08:26:30 [__init__.py:1750] Using max model len 16384
[1;36m(APIServer pid=15975)[0;0m INFO 08-20 08:26:31 [scheduler.py:222] Chunked prefill is enabled with max_num_batched_tokens=2048.
INFO 08-20 08:26:36 [__init__.py:241] Automatically detected platform cuda.
[1;36m(EngineCore_0 pid=16412)[0;0m INFO 08-20 08:26:37 [core.py:636] Waiting for init message from front-end.
[1;36m(EngineCore_0 pid=16412)[0;0m INFO 08-20 08:26:37 [core.py:74] Initializing a V1 LLM engine (v0.10.1) with config: model='skt/A.X-4.0-Light', speculative_config=None, tokenizer='skt/A.X-4.0-Light', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config={}, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=16384, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_backend=''), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=skt/A.X-4.0-Light, enable_prefix_caching=True, chunked_prefill_enabled=True, use_async_output_proc=True, pooler_config=None, compilation_config={"level":3,"debug_dump_path":"","cache_dir":"","backend":"","custom_ops":[],"splitting_ops":["vllm.unified_attention","vllm.unified_attention_with_output","vllm.mamba_mixer2"],"use_inductor":true,"compile_sizes":[],"inductor_compile_config":{"enable_auto_functionalized_v2":false},"inductor_passes":{},"cudagraph_mode":1,"use_cudagraph":true,"cudagraph_num_of_warmups":1,"cudagraph_capture_sizes":[512,504,496,488,480,472,464,456,448,440,432,424,416,408,400,392,384,376,368,360,352,344,336,328,320,312,304,296,288,280,272,264,256,248,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"pass_config":{},"max_capture_size":512,"local_cache_dir":null}
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] EngineCore failed to start.
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] Traceback (most recent call last):
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/v1/engine/core.py", line 691, in run_engine_core
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] engine_core = EngineCoreProc(*args, **kwargs)
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/v1/engine/core.py", line 492, in __init__
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] super().__init__(vllm_config, executor_class, log_stats,
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/v1/engine/core.py", line 80, in __init__
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] self.model_executor = executor_class(vllm_config)
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/executor/executor_base.py", line 54, in __init__
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] self._init_executor()
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/executor/uniproc_executor.py", line 48, in _init_executor
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] self.collective_rpc("init_device")
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/executor/uniproc_executor.py", line 58, in collective_rpc
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] answer = run_method(self.driver_worker, method, args, kwargs)
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/utils/__init__.py", line 3007, in run_method
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] return func(*args, **kwargs)
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] ^^^^^^^^^^^^^^^^^^^^^
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/worker/worker_base.py", line 603, in init_device
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] self.worker.init_device() # type: ignore
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] ^^^^^^^^^^^^^^^^^^^^^^^^^
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] File "/usr/local/lib/python3.11/dist-packages/vllm/v1/worker/gpu_worker.py", line 179, in init_device
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] raise ValueError(
[1;36m(EngineCore_0 pid=16412)[0;0m ERROR 08-20 08:26:38 [core.py:700] ValueError: Free memory on device (2.96/44.34 GiB) on startup is less than desired GPU memory utilization (0.9, 39.91 GiB). Decrease GPU memory utilization or reduce GPU memory used by other processes.
### API Usage
## Usage with PEFT
## Performance
- **Hot-swap Speed**: 0.18s (switching between base and LoRA)
- **GPU Memory**: ~14.8 GiB
- **Inference Speed**: 0.18-0.19s per request after warmup
## Files
- : LoRA configuration
- : LoRA weights (SafeTensors format)
- Tokenizer files included for convenience
|
mradermacher/Rubicon-Preview-GGUF
|
mradermacher
| 2025-08-20T08:25:34Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:inclusionAI/Rubicon-Preview",
"base_model:quantized:inclusionAI/Rubicon-Preview",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-08-19T18:34:21Z |
---
base_model: inclusionAI/Rubicon-Preview
language:
- en
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/inclusionAI/Rubicon-Preview
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Rubicon-Preview-GGUF).***
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Rubicon-Preview-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q2_K.gguf) | Q2_K | 11.4 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q3_K_S.gguf) | Q3_K_S | 13.4 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q3_K_M.gguf) | Q3_K_M | 14.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q3_K_L.gguf) | Q3_K_L | 16.0 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.IQ4_XS.gguf) | IQ4_XS | 16.7 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q4_K_S.gguf) | Q4_K_S | 17.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q4_K_M.gguf) | Q4_K_M | 18.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q5_K_S.gguf) | Q5_K_S | 21.2 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q5_K_M.gguf) | Q5_K_M | 21.8 | |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q6_K.gguf) | Q6_K | 25.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Rubicon-Preview-GGUF/resolve/main/Rubicon-Preview.Q8_0.gguf) | Q8_0 | 32.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
TimJaspersTue/SurgeNetModels
|
TimJaspersTue
| 2025-08-20T08:24:30Z | 0 | 0 | null |
[
"arxiv:2210.13452",
"arxiv:1602.03012",
"arxiv:2110.12555",
"arxiv:2006.07164",
"arxiv:2212.04582",
"arxiv:2305.07152",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2024-06-19T10:52:11Z |
---
license: cc-by-nc-4.0
---
<div align="center">
<h1>Publications</h1>
<h3>Scaling up self-supervised learning for improved surgical foundation models</h3>
[Tim J.M. Jaspers](https://timjaspers0801.github.io/)<sup>1* :email:</sup>, [Ronald L.P.D. de Jong](https://scholar.google.com/citations?user=We226GgAAAAJ&hl=en)<sup>2*</sup>,
[Yiping Li](https://research.tue.nl/nl/persons/yiping-li/publications/)<sup>2</sup>, [Carolus H.J. Kusters](https://chjkusters.github.io/)<sup>1</sup>, Franciscus H.A. Bakker<sup>5</sup>,
Romy C. van Jaarsveld<sup>3</sup>, Gino M. Kuipers<sup>3</sup>, Richard<sup>3</sup>, Jelle P. Ruurda<sup>3</sup>,
Willem M. Brinkman<sup>4</sup>, Josien P.W. Pluim<sup>2</sup>,
Peter H.N. de With<sup>1</sup>, Marcel Breeuwer<sup>2</sup>, [Yasmina Al Khalil](https://scholar.google.com/citations?user=m6co7N0AAAAJ&hl=en)<sup>2</sup>, [Fons van der Sommen](https://scholar.google.com/citations?user=qFiLkCAAAAAJ&hl=en)<sup>1</sup>
<sup>1</sup> Department of Electrical Engineering, Video Coding & Architectures, Eindhoven University of Technology \
<sup>2</sup> Department of Biomedical Engineering, Medical Image Analysis, Eindhoven University of Technology, Eindhoven, The Netherlands \
<sup>3</sup> Department of Surgery, University Medical Center Utrecht, Utrecht, The Netherlands \
<sup>4</sup> Department of Oncological Urology, University Medical Center Utrecht, Utrecht, The Netherlands \
<sup>5</sup> Department of Surgery, Catharina Hospital, Eindhoven, The Netherlands
<sup>*</sup> Both authors attributed equally \
(<sup>:email:</sup>) corresponding author
*arxiv* <br /> ([Article](https://doi.org/10.1016/j.media.2024.103348))
<h3> Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision</h3>
[Tim J.M. Jaspers](https://timjaspers0801.github.io/)<sup>1 :email:</sup>, [Ronald L.P.D. de Jong](https://scholar.google.com/citations?user=We226GgAAAAJ&hl=en)<sup>2</sup>,
[Yasmina Al Khalil](https://scholar.google.com/citations?user=m6co7N0AAAAJ&hl=en)<sup>2</sup>, Tijn Zeelenberg <sup>1</sup>, [Carolus H.J. Kusters](https://chjkusters.github.io/)<sup>1</sup>, Franciscus H.A. Bakker<sup>5</sup>,
[Yiping Li](https://research.tue.nl/nl/persons/yiping-li/publications/)<sup>2</sup>, Romy C. van Jaarsveld<sup>3</sup>, Jelle P. Ruurda<sup>3</sup>, Willem M. Brinkman<sup>4</sup>,
Peter H.N. de With<sup>1</sup>, [Fons van der Sommen](https://scholar.google.com/citations?user=qFiLkCAAAAAJ&hl=en)<sup>1</sup>,
*Second Workshop on Data Engineering in Medical Imaging (DEMI) - Satellite Event MICCAI 2024* <br /> ([Proceeding](https://link.springer.com/chapter/10.1007/978-3-031-73748-0_5))
<sup>1</sup> Department of Electrical Engineering, Video Coding & Architectures, Eindhoven University of Technology \
<sup>2</sup> Department of Biomedical Engineering, Medical Image Analysis, Eindhoven University of Technology, Eindhoven, The Netherlands \
<sup>3</sup> Department of Surgery, University Medical Center Utrecht, Utrecht, The Netherlands \
<sup>4</sup> Department of Oncological Urology, University Medical Center Utrecht, Utrecht, The Netherlands \
<sup>5</sup> Department of Surgery, Catharina Hospital, Eindhoven, The Netherlands
(<sup>:email:</sup>) corresponding author
<h1>Abstract</h1>
Foundation models have revolutionized computer vision by achieving state-of-the-art
performance across diverse tasks through large-scale pretraining on extensive datasets.
However, their application in surgical computer vision has been limited. This study
addresses this gap by introducing SurgeNetXL, a novel surgical foundation model that
sets a new benchmark in surgical computer vision. Trained on the largest reported surgical
dataset to date, comprising over 4.7 million video frames, SurgeNetXL achieves
consistent top-tier performance across six datasets spanning four surgical procedures
and three tasks, including semantic segmentation, phase recognition, and critical view
of safety (CVS) classification. Compared to the best-performing surgical foundation
models, SurgeNetXL shows mean improvements of 2.4, 8.95, and 12.6% for semantic segmentation,
phase recognition, and CVS classification, respectively. Additionally,
SurgeNetXL outperforms the best-performing ImageNet-based variants by 14.4, 4.0,
and 1.6% in the respective tasks. In addition to advancing model performance, this work
provides key insights into scaling pretraining datasets, extending training durations, and
optimizing model architectures specifically for surgical computer vision. These findings
pave the way for improved generalizability and robustness in data-scarce scenarios, offering
a comprehensive framework for future research in this domain.
<h1>Results</h1>
The following figures are from our publications, showcasing the performance of our introduced foundation model
across diverse surgical tasks and procedures. These results demonstrate the model’s state-of-the-art
performance on a variety of downstream tasks, reflecting its versatility and robustness in handling
datasets from multiple surgical procedures.
Figure 1 and Figure 2 illustrate comparative rankings of our model against existing foundation models,
highlighting its superior generalization capabilities across datasets. Figure 3 provides a t-SNE visualization,
showcasing the clear cluster separation per specific dataset achieved by the model’s feature embeddings,
further emphasizing its effectiveness in capturing meaningful representations.
<div style="display: flex; justify-content: space-around; align-items: center; gap: 20px;">
<div style="text-align: center;">
<img src="figures/radar_ranks.png" alt="Fig 2" width="400" height="300">
<p><strong>Fig 1:</strong> Radar chart showing model ranks across datasets.</p>
</div>
<div style="text-align: center;">
<img src="figures/ranking_blob_all.png" alt="Fig 3" width="400" height="300">
<p><strong>Fig 2:</strong> Blob chart representing ranking metrics for models.</p>
</div>
</div>
<div style="text-align: center; margin-top: 20px;">
<img src="figures/TSNE.png" alt="Fig 3" width="600">
<p><strong>Fig 3:</strong> t-SNE visualization of feature embeddings showing cluster separation across datasets.</p>
</div>
<h1>Models</h1>
The models used in this study are based on the [MetaFormer](https://arxiv.org/abs/2210.13452) architecture. The models are trained using a self-supervised learning
approach on the SurgeNetXL dataset and its variations,
introduced this in the following [paper](https://). All model weights can be downloaded from the table below.
| Model | Backbone | Epochs | Teacher Backbone | Full DINO checkpoint |
|-----------------|------------|--------|-------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------|
| SurgeNetXL | CaFormer | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNetXL_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNetXL_checkpoint0050.pth?download=true) |
| SurgeNetSmall | CaFormer | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNetSmall_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNetSmall_checkpoint0050.pth?download=true) |
| SurgeNetCholec | CaFormer | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/CHOLEC_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/CHOLEC_checkpoint0050.pth?download=true) |
| SurgeNetRAMIE | CaFormer | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/RAMIE_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/RAMIE_checkpoint0050.pth?download=true) |
| SurgeNetRARP | CaFormer | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/RARP_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/RARP_checkpoint0050.pth?download=true) |
| SurgeNetPublic | CaFormer | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/Public_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/Public_checkpoint0050.pth?download=true) |
| SurgeNet | CaFormer | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_checkpoint0050.pth?download=true) |
| SurgeNet | ConvNextv2 | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_ConvNextv2_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_ConvNextv2_checkpoint0050.pth?download=true) |
| SurgeNet | PVTv2 | 50 | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_PVTv2_checkpoint_epoch0050_teacher.pth?download=true) | [Download](https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_PVTv2_checkpoint0050.pth?download=true) |
<h1>Loading Models</h1>
The weights from the teacher network can be used to initialize either your classification or segmentation model using the following code snippet:
</div>
```python
import torch
from metaformer import caformer_s18, MetaFormerFPN
from convnextv2 import convnextv2_tiny, ConvNextFPN
from pvtv2 import pvt_v2_b2, PVTV2FPN
urls = {
"ImageNet1k": "https://huggingface.co/sail/dl/resolve/main/caformer/caformer_s18.pth",
"SurgeNetXL": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNetXL_checkpoint_epoch0050_teacher.pth?download=true",
"SurgeNet": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_checkpoint_epoch0050_teacher.pth?download=true",
"SurgeNet-Small": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNetSmall_checkpoint_epoch0050_teacher.pth?download=true",
"SurgeNet-CHOLEC": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/CHOLEC_checkpoint_epoch0050_teacher.pth?download=true",
"SurgeNet-RAMIE": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/RAMIE_checkpoint_epoch0050_teacher.pth?download=true",
"SurgeNet-RARP": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/RARP_checkpoint_epoch0050_teacher.pth?download=true",
"SurgeNet-Public": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/Public_checkpoint0050.pth?download=true",
"SurgeNet-ConvNextv2": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_ConvNextv2_checkpoint_epoch0050_teacher.pth?download=true",
"SurgeNet-PVTv2": "https://huggingface.co/TimJaspersTue/SurgeNetModels/resolve/main/SurgeNet_PVTv2_checkpoint_epoch0050_teacher.pth?download=true",
}
# Metaformer model
classification_model = caformer_s18(num_classes=12, pretrained='SurgeNet', pretrained_weights=urls['SurgeNetXL'])
segmentation_model = MetaFormerFPN(num_classes=12, pretrained='SurgeNet', pretrained_weights=urls['SurgeNetXL'])
# ConvNextv2 model
classification_model = convnextv2_tiny(num_classes=12, pretrained_weights=urls['SurgeNet-ConvNextv2'])
segmentation_model = ConvNextFPN(num_classes=12, pretrained_weights=urls['SurgeNet-ConvNextv2'])
# PVTv2 model
classification_model = pvt_v2_b2(num_classes=12, pretrained_weights=urls['SurgeNet-PVTv2'])
segmentation_model = PVTV2FPN(num_classes=12, pretrained_weights=urls['SurgeNet-PVTv2'])
```
<div align="center">
Note: If your want a different version of SurgeNet weights (e.g. SurgeNet-Small), you can replace the `pretrained_weights` argument with the desired url (leave the `pretrained` argument as it is).
<h1>Surgical Youtube Dataset</h1>
A key contribution of our research is the Surgical YouTube dataset, which enhanced our foundation model's
performance. This curated dataset contains 2,074,234 frames sampled from 23 distinct surgical procedures
and is publicly available at [huggingface datasets.](https://huggingface.co/datasets/TimJaspersTue/SurgeNetYoutube)
This datasets is a large part of our SurgeNetXL dataset, which also includes other opensource datasets.
| Procedure-specific subset | Dataset | Procedure | #videos | #frames | Public |
|---------------------------|----------------------------------------------------------------|-----------|---------|-----------|--------|
| **SurgeNetCholec** | Cholec80 ([Twinnanda et al., 2017b](https://arxiv.org/abs/1602.03012)) | Laparoscopic Cholecystectomy | 76 | 179,164 | Yes |
| | HeiChole ([Maier-Hein et al., 2021](https://www.synapse.org/Synapse:syn25101790/wiki/608802)) | Laparoscopic Cholecystectomy | 30 | 53,427 | Yes |
| | hSDB-Chole ([Yoon et al., 2021](https://arxiv.org/abs/2110.12555)) | Laparoscopic Cholecystectomy | 24 | 18,064 | Yes |
| **SurgeNetRAMIE** | RAMIE-UMCU | RA Esophagectomy | 28 | 377,287 | No |
| **SurgeNetRARP** | ESAD [Bawa et al., 2021](https://arxiv.org/abs/2006.07164) | RA Esophagectomy | 28 | 47,282 | Yes |
| | PSI-AVA [Valderrama et al., 2022](https://arxiv.org/abs/2212.04582) | RA Prostatectomy | 8 | 73,618 | Yes |
| | RARP-AvL | RA Prostatectomy | 8 | 261,516 | No |
| **Others** | DSAD ([Carstens et al., 2023](https://www.nature.com/articles/s41597-022-01719-2)) | RA Rectal Resection/Extirpation | 32 | 14,623 | Yes |
| | GLENDA ([Leibetseder et al., 2020](https://link.springer.com/chapter/10.1007/978-3-030-37734-2_36)) | Gynecologic Laparoscopy | 400 | 25,682 | Yes |
| | LapGyn4 ([Leibetseder et al., 2018](https://dl.acm.org/doi/10.1145/3204949.3208127)) | Gynecologic Laparoscopy | 500 | 59,616 | Yes |
| | MultiBypass140 ([Lavanchy et al., 2024](https://github.com/CAMMA-public/MultiBypass140)) | Laparoscopic Gastric Bypass Surgery | 140 | 749,419 | Yes |
| | hSDB-Gastric ([Yoon et al., 2021](https://arxiv.org/abs/2110.12555)) | RA Gastrectomy | 24 | 35,576 | Yes |
| | SurgToolLoc2022 ([Zia et al., 2023](https://arxiv.org/abs/2305.07152)) | 11 different RA porcine procedures | N/A | 741,516 | Yes |
| | YouTube [ours](https://huggingface.co/datasets/TimJaspersTue/SurgeNetYoutube) | 23 identified procedures | 3,253 | 2,074,234 | Yes |
| SurgeNetXL variations | Dataset | Procedure | #videos | #frames | Public |
|-----------------------|------------------------------------------------------------|---------------------------------------------------------|---------|---------|--------|
| **SurgeNetSmall** | 10% of the above (excluding YouTube) | All of the above (excluding YouTube) | \>1345 | 263,679 | Partly |
| **SurgeNetPublic** | All public datasets (excluding YouTube & private datasets) | All of the above (excluding YouTube & RA Esophagectomy) | \>1238 | 1,997,987 | Yes |
| **SurgeNet** | All of the above (excluding YouTube) | All of the above (excluding YouTube) | \>1345 | 2,636,790 | Partly |
| **SurgeNetXL** | All of the above | All of the above | \>4598 | 4,711,024 | Partly |
<h1>Acknowledgements</h1>
Our implementation of the feature pyramid network is based on the [pytorch segmentation models](https://segmentation-modelspytorch.readthedocs.io/en/latest/) library.
Pretraining on SurgeNet was performed using the code provided with the [DINO](https://github.com/facebookresearch/dino) publication.
We have used the code of Schmidgall et al. (2024) to obtain the youtube videos, this code can be found [here](https://github.com/SamuelSchmidgall/GSViT).
<h1>Citation</h1>
If you find our work useful in your research please consider citing our paper:
</div>
```bibtex
@msc{Jaspers2025,
title={Scaling up self-supervised learning for improved surgical foundation models},
year={2025}
}
```
```bibtex
@inbook{Jaspers2024,
title={Exploring the Effect of Dataset Diversity in Self-supervised Learning for Surgical Computer Vision},
ISBN={9783031737480},
ISSN={1611-3349},
url={http://dx.doi.org/10.1007/978-3-031-73748-0_5},
DOI={10.1007/978-3-031-73748-0_5},
booktitle={Data Engineering in Medical Imaging},
publisher={Springer Nature Switzerland},
author={Jaspers, Tim J. M. and de Jong, Ronald L. P. D. and Al Khalil, Yasmina and Zeelenberg, Tijn and Kusters, Carolus H. J. and Li, Yiping and van Jaarsveld, Romy C. and Bakker, Franciscus H. A. and Ruurda, Jelle P. and Brinkman, Willem M. and De With, Peter H. N. and van der Sommen, Fons},
year={2024},
month=oct, pages={43–53} }
```
|
lavinzco/blockassist-bc-thick_climbing_giraffe_1755674642
|
lavinzco
| 2025-08-20T08:23:45Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thick climbing giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:23:31Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thick climbing giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
mang3dd/blockassist-bc-tangled_slithering_alligator_1755676496
|
mang3dd
| 2025-08-20T08:20:59Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tangled slithering alligator",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:20:55Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tangled slithering alligator
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755676297
|
katanyasekolah
| 2025-08-20T08:19:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"silky sprightly cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:19:46Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- silky sprightly cassowary
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Medved444/blockassist-bc-bellowing_finicky_manatee_1755676845
|
Medved444
| 2025-08-20T08:19:43Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"bellowing finicky manatee",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:19:25Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- bellowing finicky manatee
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
PavanSakthivel/Taxi-v3
|
PavanSakthivel
| 2025-08-20T08:19:21Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-08-20T08:19:18Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.52 +/- 2.77
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="PavanSakthivel/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Uppal-Farm-Girl-Viral-Video-Link-Orginal/New.full.videos.Uppal.Farm.Girl.Viral.Video.Official.Tutorial
|
Uppal-Farm-Girl-Viral-Video-Link-Orginal
| 2025-08-20T08:18:45Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T08:18:37Z |
<a href="https://sdu.sk/AyL"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝗦𝗶𝗴𝗻 𝗨𝗽 𝘁𝗼 𝙁𝙪𝙡𝙡 𝗪𝗮𝘁𝗰𝗵 𝙑𝙞𝙙𝙚𝙤❤️❤️)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►✅𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐥𝐢𝐧𝐤)</a>
|
Original-Uppal-Farm-Girl-Viral-Video-Clips/New.full.videos.Uppal.Farm.Girl.Viral.Video.Official.Tutorial
|
Original-Uppal-Farm-Girl-Viral-Video-Clips
| 2025-08-20T08:17:11Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T08:16:59Z |
<a href="https://sdu.sk/AyL"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝗦𝗶𝗴𝗻 𝗨𝗽 𝘁𝗼 𝙁𝙪𝙡𝙡 𝗪𝗮𝘁𝗰𝗵 𝙑𝙞𝙙𝙚𝙤❤️❤️)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►✅𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐥𝐢𝐧𝐤)</a>
|
hakimjustbao/blockassist-bc-raging_subtle_wasp_1755676181
|
hakimjustbao
| 2025-08-20T08:16:35Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"raging subtle wasp",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:16:31Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- raging subtle wasp
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VIDEOS-19-fooni-fun-Viral-Video-Clip-XX/New.full.videos.fooni.fun.Viral.Video.Official.Tutorial
|
VIDEOS-19-fooni-fun-Viral-Video-Clip-XX
| 2025-08-20T08:16:18Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T08:16:11Z |
<a href="https://sdu.sk/AyL"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝗦𝗶𝗴𝗻 𝗨𝗽 𝘁𝗼 𝙁𝙪𝙡𝙡 𝗪𝗮𝘁𝗰𝗵 𝙑𝙞𝙙𝙚𝙤❤️❤️)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►✅𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐥𝐢𝐧𝐤)</a>
|
manusiaperahu2012/blockassist-bc-roaring_long_tuna_1755676003
|
manusiaperahu2012
| 2025-08-20T08:16:07Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"roaring long tuna",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:16:03Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- roaring long tuna
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
unitova/blockassist-bc-zealous_sneaky_raven_1755676050
|
unitova
| 2025-08-20T08:15:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"zealous sneaky raven",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:15:48Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- zealous sneaky raven
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
armonio/my-bert-fine-tuned1
|
armonio
| 2025-08-20T08:15:46Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-08-20T08:15:30Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
indoempatnol/blockassist-bc-fishy_wary_swan_1755676079
|
indoempatnol
| 2025-08-20T08:13:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"fishy wary swan",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:13:45Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- fishy wary swan
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
AnerYubo/blockassist-bc-prowling_pudgy_gerbil_1755677597
|
AnerYubo
| 2025-08-20T08:13:19Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"prowling pudgy gerbil",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:13:18Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- prowling pudgy gerbil
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
AnerYubo/blockassist-bc-chattering_regal_bat_1755677589
|
AnerYubo
| 2025-08-20T08:13:13Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"chattering regal bat",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:13:10Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- chattering regal bat
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
minchai23/test_dataset_modify_time
|
minchai23
| 2025-08-20T08:12:54Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-08-20T08:12:54Z |
---
license: apache-2.0
---
|
insomniaclivec1/blockassist-bc-unseen_marine_mandrill_1755675388
|
insomniaclivec1
| 2025-08-20T08:12:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"unseen marine mandrill",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:12:48Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- unseen marine mandrill
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ChavyvAkvar/Liquid-Thinking
|
ChavyvAkvar
| 2025-08-20T08:12:20Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"lfm2",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T16:28:34Z |
---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
thanobidex/blockassist-bc-colorful_shiny_hare_1755675918
|
thanobidex
| 2025-08-20T08:11:57Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"colorful shiny hare",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:11:54Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- colorful shiny hare
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
calegpedia/blockassist-bc-stealthy_slimy_rooster_1755675981
|
calegpedia
| 2025-08-20T08:11:25Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stealthy slimy rooster",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:11:22Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stealthy slimy rooster
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
germanlunichh/blockassist-bc-mute_shaggy_alligator_1755675407
|
germanlunichh
| 2025-08-20T08:10:37Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mute shaggy alligator",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:10:34Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- mute shaggy alligator
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
coelacanthxyz/blockassist-bc-finicky_thriving_grouse_1755675696
|
coelacanthxyz
| 2025-08-20T08:10:34Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"finicky thriving grouse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T08:10:27Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- finicky thriving grouse
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.